WO2018173401A1

WO2018173401A1 - Information processing device, information processing method, and program

Info

Publication number: WO2018173401A1
Application number: PCT/JP2017/046266
Authority: WO
Inventors: 脇田　能宏; 直也佐塚
Original assignee: ソニー株式会社
Priority date: 2017-03-21
Filing date: 2017-12-22
Publication date: 2018-09-27
Also published as: EP3598945B1; CN110381833B; CN110381833A; JP7024780B2; US20210282708A1; EP3598945A1; EP3598945A4; JPWO2018173401A1

Abstract

[Problem] To provide an information processing device capable of accurately estimating energy expenditure. [Solution] Provided is an information processing device which is provided with an acquisition unit for acquiring body features of a user and a device for estimation based on a relationship between heart rate and energy expenditure. In accordance with the body features of the user, the device for estimation estimates the energy expended in an activity performed by the user on the basis of the heart rate of the user.

Description

Information processing apparatus, information processing method, and program

The present disclosure relates to an information processing apparatus, an information processing method, and a program.

In recent years, there has been a demand for a device that can easily grasp the energy consumed by daily activities and sports for health maintenance, physical fitness development, dieting and the like. As an example of such a device, a device that measures the user's heart rate or pulse rate and estimates the energy consumption based on the relationship between the heart rate corresponding to the exercise intensity at the time of measurement and the energy consumption. Can be mentioned. Further, as another example, energy consumption based on attribute information such as the user's height, weight, age, sex, etc. and the exercise intensity obtained by the accelerometer worn by the user or the user's moving distance An apparatus for estimating As an example of the latter, a portable health care device disclosed in Patent Document 1 below can be cited. The apparatus disclosed in the following Patent Document 1 can estimate with high accuracy when estimating the energy consumption by the user's walking.

JP 2002-45352 A

However, according to the above-described apparatus, it has been difficult to estimate with high accuracy the energy consumed in daily activities, which is a series of various short-time exercises.

Therefore, the present disclosure proposes a new and improved information processing apparatus, information processing method, and program capable of estimating energy consumption with high accuracy.

According to the present disclosure, an acquisition unit that acquires a physical characteristic of a user, and an estimator based on a relationship between the number of beats and energy consumption, the estimator according to the physical characteristic of the user, There is provided an information processing apparatus that estimates energy consumption by an activity performed by a user from the number of beats of the user.

Further, according to the present disclosure, based on the relationship between the user's body characteristics and the number of beats according to the user's body characteristics and the energy consumption, An information processing method is provided, including estimating energy consumption due to the activity.

Furthermore, according to the present disclosure, based on the function of acquiring a user's physical characteristics and the relationship between the number of pulsations and energy consumption according to the user's physical characteristics, the user performs from the number of pulsations of the user. And a program for causing a computer to realize the function of estimating the energy consumed by the activity.

As described above, according to the present disclosure, it is possible to provide an information processing apparatus, an information processing method, and a program that can estimate energy consumption with high accuracy.

Note that the above effects are not necessarily limited, and any of the effects shown in the present specification, or other effects that can be grasped from the present specification, together with or in place of the above effects. May be played.

2 is an explanatory diagram illustrating a configuration example of an information processing system 1 according to a first embodiment of the present disclosure. FIG. It is a block diagram showing the composition of wearable device 10 concerning the embodiment. 2 is an explanatory diagram illustrating an example of an appearance of a wearable device 10 according to the embodiment. FIG. It is explanatory drawing which shows another example of the external appearance of the wearable device 10 which concerns on the embodiment. It is explanatory drawing which shows an example of the mounting state of the wearable device 10 which concerns on the embodiment. It is a block diagram which shows the structure of the server 30 which concerns on the embodiment. It is a block diagram showing the composition of user terminal 50 concerning the embodiment. It is explanatory drawing which shows an example of the external appearance and usage pattern of the user terminal 50 which concerns on the embodiment. It is explanatory drawing (the 1) for demonstrating operation | movement of the learning part 132 which concerns on the embodiment. It is explanatory drawing (the 2) for demonstrating operation | movement of the learning part 132 which concerns on the same embodiment. It is explanatory drawing (the 1) for demonstrating operation | movement of the likelihood estimator 236 which concerns on the embodiment. It is explanatory drawing (the 2) for demonstrating operation | movement of the likelihood estimator 236 which concerns on the same embodiment. FIG. 11 is an explanatory diagram (No. 3) for explaining the operation of the likelihood estimator 236 according to the embodiment. It is explanatory drawing for demonstrating operation | movement of the estimation part 136 which concerns on the same embodiment. It is a flowchart explaining an example of the learning stage of the information processing method which concerns on the embodiment. It is a flowchart explaining an example of the presumed stage of the information processing method concerning the embodiment. It is explanatory drawing explaining an example of the display screen 800 used at the time of acquisition of time series data. It is explanatory drawing explaining an example of the display screen 802 used at the time of acquisition of time series data. It is explanatory drawing explaining an example of the display screen 804 used when acquiring time-sequential data. It is explanatory drawing explaining an example of the display screen 806 used at the time of acquisition of time series data. It is explanatory drawing explaining the method of guide | inducing exercise | movement with respect to a user in the time of acquisition of time series data. It is explanatory drawing explaining an example of the display screen 808 used at the time of acquisition of the time series data by another method. It is explanatory drawing explaining an example of the display screen 810 used in the time of acquisition of the time series data by another method. It is explanatory drawing explaining an example of the display screen 812 used when acquiring the time series data by another method. It is explanatory drawing explaining an example of the display screen 814 used at the time of acquisition of the time series data by another method. It is explanatory drawing explaining the other method of guide | inducing exercise | movement with respect to a user at the time of acquisition of time series data. 10 is an explanatory diagram illustrating an example of a display screen 820 according to Embodiment 1. FIG. 10 is an explanatory diagram illustrating an example of a display screen 822 according to Embodiment 1. FIG. 10 is an explanatory diagram illustrating an example of a display screen 824 according to Embodiment 2. FIG. 10 is an explanatory diagram illustrating an example of a display screen 826 according to Embodiment 2. FIG. 10 is an explanatory diagram illustrating an example of a display screen 828 according to Embodiment 2. FIG. 10 is an explanatory diagram illustrating an example of a display screen 830 according to Embodiment 2. FIG. It is explanatory drawing which shows the time-dependent change 90 and the time-dependent change 92 of the heart rate obtained by examination of the present inventors. FIG. 3 is a block diagram illustrating an example of a hardware configuration of an information processing apparatus 900 according to an embodiment of the present disclosure.

Hereinafter, preferred embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. In addition, in this specification and drawing, about the component which has the substantially same function structure, duplication description is abbreviate | omitted by attaching | subjecting the same code | symbol.

In the present specification and drawings, a plurality of constituent elements having substantially the same or similar functional configuration may be distinguished by attaching different numbers after the same reference numerals. However, when it is not necessary to particularly distinguish each of a plurality of constituent elements having substantially the same or similar functional configuration, only the same reference numerals are given. In addition, similar components in different embodiments may be distinguished by attaching different alphabets after the same reference numerals. However, if it is not necessary to distinguish each similar component, only the same reference numerals are given.

In the following description, “beat rate” includes a heart rate and a pulse rate, and these heart rate and pulse rate can be measured by a heart rate sensor or a pulse sensor.

The description will be made in the following order.
1. 1. Background to creation of an embodiment according to the present disclosure Embodiment according to the present disclosure 2.1. Overview of information processing system 1 according to the present embodiment 2.2. Configuration of wearable device 10 according to the present embodiment 2.3. Configuration of server 30 according to the present embodiment 2.4. Configuration of user terminal 50 according to the present embodiment 2.5. Configuration of control unit 130 according to the present embodiment 2.6. 2. Information processing method according to this embodiment Example according to this embodiment 3.1. Example 1
3.2. Example 2
4). Summary 5. 5. Hardware configuration Supplement

<< 1. Background to the creation of an embodiment according to the present disclosure >>
First, before describing the embodiment according to the present disclosure, the background to the creation of the embodiment according to the present disclosure by the inventors, that is, the examination performed by the inventors will be described.

The present inventors examined a method for estimating energy consumption based on user activities. First, a method for measuring energy consumption will be described. There are two main methods for measuring energy consumption: direct calorimetry, which directly measures the generated heat, and indirect calorimetry, which indirectly measures heat from the consumption of oxygen used in the body. There are two types of measurement methods.

In the “direct calorimetry”, the energy consumed by the human body is dissipated as heat from the human body, so the energy consumption is measured by directly measuring the heat dissipated from the human body. However, since the measuring device used in the “direct thermal power measurement method” is very large and restricts the activity of the subject to be measured, the situation where energy consumption can be measured by the “direct thermal power measurement method” is limited. The

On the other hand, the “indirect calorimetry” measures the oxygen concentration and carbon dioxide concentration in the user's breath and calculates the energy consumption from these measurement results. Generation of energy in the human body is done by breaking down fats and sugars taken from food, etc., but in most cases, oxygen taken into the human body by breathing is necessary for such decomposition. Become. Therefore, the consumption amount of oxygen substantially corresponds to the consumed energy. Further, carbon dioxide is generated by such decomposition in the human body, and the generated carbon dioxide is discharged from the human body as part of exhalation. Therefore, it is possible to know the energy consumption by measuring the oxygen concentration and carbon dioxide concentration in the exhaled breath and determining the amount of oxygen consumed in the user's human body from these measured values. That is, the “indirect calorimetry” is not a method for directly measuring the amount of heat generated in the human body, but it is possible to grasp the energy consumption almost accurately by the above-described metabolic mechanism in the human body. Since the breath measurement device used in the “indirect calorimetry” is simpler than the device used in the “direct heat measurement method” described above, the “indirect calorimetry” is a method for measuring energy consumption. It is common to be used. In the following description, it is assumed that the actual measurement value of energy consumption is measured by the above-mentioned “indirect calorimetry”.

However, in the “indirect calorimetry”, it is necessary to measure the oxygen concentration and carbon dioxide concentration in the exhaled breath, so the subject wears a mask or the like. Therefore, although the “indirect calorimetry” is simpler than the “direct calorimetry”, it is difficult for a general user to easily perform the measurement. Therefore, the present inventors have made extensive studies on a method for obtaining energy consumption by using an easily measurable index. Here, the general user means a person who is not an expert such as a researcher, a doctor, or an athlete.

Based on such a situation, the present inventors know the energy consumption using the number of beats (specifically, heart rate or pulse rate) that is generally said to be highly correlated with the energy consumption. The method was examined repeatedly. Specifically, in various parts of the body, metabolic activities are performed to supplement the consumed energy. At this time, oxygen is consumed and carbon dioxide is generated. It is known that the amount of oxygen consumed and the amount of carbon dioxide produced are not completely proportional but have a monotonic relationship that is almost proportional. The heartbeat is the heart muscles contracting and expanding at a constant rhythm and pulsating.By the heartbeat, blood is sent to the whole body through the arteries, so that oxygen required for metabolism is supplied to each organ of the body. Supplied. In addition, carbon dioxide produced by metabolism elutes in the blood, collects in the heart via veins, and is discharged into the exhalation by gas exchange by the lungs. The heart rate is known to increase or decrease depending on the need to enhance blood circulation in the body, but in relation to energy consumption, the mechanism is linked to the concentration of blood carbon dioxide. It is known that heart rate is controlled. In other words, the heart rate has a property that its numerical value increases or decreases according to the necessity of carbon dioxide excretion, which is one of the necessity for enhancing blood circulation in the body. Therefore, the heart rate has a strong correlation with the consumed energy via the carbon dioxide production amount, and is useful information for estimating the consumed energy. In the following description, the heart rate means the number of pulsations in the heart per unit time, and the pulse rate is a change in pressure that occurs on the inner wall of the artery due to blood being sent to the whole body through the artery. This refers to the number of pulsations of an artery appearing on the body surface or the like in a unit time.

In recent years, heart rate sensors that measure heart rate and pulse sensors that measure pulse rate have become compact, and these heart rate sensors and pulse sensors are worn on the user's body and do not limit the user's activities. It became possible to measure the number or pulse rate. For these reasons, the present inventors have studied a method for obtaining energy consumption using the number of beats (heart rate or pulse rate).

Specifically, in the method first examined by the present inventors, the heart rate of the user is measured by a heart rate sensor, and the consumed energy is estimated using linear regression or the like based on the measured heart rate. According to the study by the present inventors, the above-described method is high because, for example, when estimating energy consumption in training using a cardio bike type training device, the heart rate changes according to exercise intensity. It was found that the estimation accuracy can be obtained. However, according to the method described above, it has been found that the estimation accuracy is lowered when the energy consumption at rest is estimated. This is considered to be due to the fact that the heart rate fluctuates not only due to exercise intensity but also due to psychological factors such as tension and excitement.

Therefore, the present inventors examined a method for improving the above-described method and estimating energy consumption using not only the heart rate by the heart rate sensor but also the exercise intensity detected by the acceleration sensor. Specifically, one of the methods examined by the present inventors is a method of adjusting the contribution rate of the exercise intensity in the linear regression equation for estimating the consumed energy from the heart rate based on the detected exercise intensity. is there. In this method, an attempt is made to improve the estimation accuracy of energy consumption by adjusting the contribution rate. In addition, another one of the methods considered is based on the exercise intensity detected by the acceleration sensor, classifying the current user activity state into several types of activity patterns such as a resting state, a walking state, and a running state, This is a method of switching the regression equation to be used according to the classified activity pattern. In this method, when there is a limit in estimation using a predetermined regression equation, an attempt is made to improve the estimation accuracy of energy consumption by using another regression equation that is optimal for the state.

However, when the present inventors have repeatedly studied the above-described method, it has been found that there is a limit to improving the estimation accuracy of energy consumption. More specifically, the energy consumption estimated from the heart rate using the above-mentioned method depends on the user's activity content, etc., and tends to be higher than the actual energy consumption. It was found that it was difficult to improve the estimation accuracy. Furthermore, when estimating the total energy consumption of one user per day by the method described above, sufficient estimation accuracy can be obtained, but when estimating the energy consumption of individual short-term exercise, It was not possible to obtain sufficient estimation accuracy.

This is because the relationship between the user's heart rate and energy consumption at a certain point in time is not determined only by the user's exercise intensity or activity state at that point, but depending on the user's physical characteristics. This is because it is influenced by the contents of the user's activities and fluctuates. In the above method, since the regression equation is selected according to the exercise intensity at a certain point in time, the exercise intensity at that point is taken into consideration, but according to the physical characteristics of the user It does not consider the impact of user activity before that time. As a result, in the method described above, the energy consumption estimated from the heart rate tends to be higher than the actual energy consumption, and there is a limit to improving the estimation accuracy. Hereinafter, it will be described in detail that the relationship between the user's heart rate and energy consumption varies depending on the user's physical characteristics and is influenced by the previous user's activity content.

The inventors of the present invention intermittently exercised a subject with a predetermined exercise intensity, and performed energy measurement and heart rate measurement on the subject using an indirect calorimetry method. FIG. 33 shows a time-dependent change 90 in energy consumption and a time-dependent change 92 in heart rate obtained by the above implementation. As shown in FIG. 33, the time-dependent change 90 in energy consumption increases to a specific value due to the exercise of the subject, but when the exercise ends, it decreases to the same level as the resting state before starting the exercise. I understand that. On the other hand, the time-dependent change 92 of the heart rate also rises due to exercise, and falls as the exercise ends, as with the change 90 of energy consumption over time. However, unlike the time-dependent change 90 in energy consumption, the time-dependent change 92 in the heart rate decreases when the exercise is completed, but does not decrease to the same extent as the resting state before the start of exercise. The heart rate change 92 over time changes in the same way as the energy consumption change 92 over the first exercise, but gradually increases as the subject repeats the exercise. More specifically, as shown in FIG. 33, the change over time in the heart rate corresponding to the period in which the exercise is paused (the section 92a protruding downward in FIG. 33) repeats the exercise. Has risen according to. Further, the change over time in the heart rate corresponding to the period during which the exercise is performed (section 92b protruding upward in FIG. 33) also rises as the exercise is repeated. In other words, it became clear that fluctuations in heart rate may deviate from fluctuations in energy consumption. In other words, according to the study by the present inventors, the relationship between the heart rate and the energy consumption can be expressed by a certain regression equation before the separation occurs, but when the separation occurs, the regression is performed. It turns out that it can no longer be expressed by a formula. In the following description, the separation phenomenon is referred to as an increase phenomenon in the heart rate because only the heart rate increases. When such an increase in heart rate occurs, the energy consumption estimated by inputting the heart rate into the regression equation is higher than the actual energy consumption.

Furthermore, when the present inventors repeatedly performed the above measurement on a plurality of subjects, it was confirmed that the enhancement phenomenon has reproducibility. In addition, it was confirmed that the expression pattern of the enhancement phenomenon tends to differ depending on the subject. Specifically, when repeated exercises are performed on the same subject, when the exercise exceeds a certain threshold (specifically, when the exercise intensity of the exercise performed exceeds a certain threshold, the number of exercises exceeds the certain threshold) When the exercise time of the exercise carried out exceeds a certain threshold value), it was confirmed that the enhancement phenomenon appears reproducibly. Moreover, when the same measurement was performed with respect to different subjects, it was confirmed that the expression pattern of the enhancement phenomenon differs depending on the subject. For example, as an expression pattern of the enhancement phenomenon, when the enhancement phenomenon is observed only during a period of high exercise intensity, when the enhancement phenomenon is observed only during a period of low exercise intensity such as during exercise pause, the high exercise intensity period and low exercise intensity There is a case where the enhancement phenomenon is observed in both the intensity periods, and the enhancement phenomenon is not observed. In addition, it was confirmed that the time constant when the enhancement phenomenon was alleviated with time and after the exercise was different from subject to subject. Furthermore, when the numerous measurement results obtained by the present inventors were examined, it was found that the expression pattern of the enhancement phenomenon could be classified into several groups according to the tendency of the expression pattern of the enhancement phenomenon.

By the way, a phenomenon called “expiratory borrowing” is known as a phenomenon in which the heart rate does not decrease immediately when the exercise is finished and the patient moves to rest. Specifically, when exercising, the amount of energy per unit time consumed by the human body increases, and the amount of metabolism increases to supply the increased energy consumption. The increased amount of metabolism described above is usually covered by metabolism using oxygen, but when oxygen supply is not in time due to the limitation of cardiopulmonary function, energy is supplied by metabolism without using oxygen. Metabolism that supplies energy without using oxygen in this way is called “expiratory borrowing” or “oxygen borrowing”. This is because metabolism without oxygen accumulates products such as lactic acid in the body, so it is necessary to metabolize those products later with oxygen. In other words, metabolism without oxygen This is because the oxygen supply is consumed as a loan. As mentioned above, when “expiratory borrowing” occurs, substances such as lactic acid accumulate, so it is necessary to carry out metabolism using oxygen even after exercise, and the amount of oxygen consumed and the amount of carbon dioxide produced are at a resting level. It does not return to and prevents a decrease in heart rate. Thus, although “expiration borrowing” is a phenomenon that prevents a decrease in the heart rate after exercise, the present inventors speculate that the above-described enhancement phenomenon is not due to “expiration borrowing”. Specifically, metabolism of substances such as lactic acid produced by “exhalation” is a phenomenon accompanied by consumption of oxygen and generation of carbon dioxide, and an increase in the amount of heat consumption is observed by “indirect calorimetry”. In other words, the elimination of “expiratory borrowing” is a phenomenon in which both energy consumption and heart rate are increased, and it is impossible to explain the state in which the heart rate is increasing despite the energy consumption being reduced to a resting level. . It is considered that the above-mentioned increase phenomenon is due to a factor in which an exercise physiology model has not been established such as “expiration borrowing”, and the heart rate is increased. The present disclosure aims to avoid an estimation error in energy consumption caused by a phenomenon whose mechanism is not clarified. The increase phenomenon is the part of the heart rate increase factor excluding the factor due to carbon dioxide, but the adjustment of the heart rate is done for the purpose of adjusting the blood flow, so the increase factor of the increase phenomenon is also some kind of adaptation in the body Presumed to be done for maintenance. Therefore, the tendency of the enhancement phenomenon is considered to be determined according to various body characteristics such as cardiopulmonary function. For example, when thinking about heat excretion, it is thought that the increase in the blood flow rate for heat transport will cause an increase in heart rate, but the increase in heart rate and the duration of the increase in heart rate are Affected by cardiopulmonary function, sweating function. Specifically, if the cardiopulmonary function is enhanced or the sweating function is enhanced, the heat exhaust efficiency is increased, so that the amount of increase in heart rate is reduced and the duration is shortened. From these characteristics, it is presumed that when physical characteristics are improved by training, the enhancement phenomenon is generally suppressed, and when physical characteristics are temporarily deteriorated due to poor physical condition, it is normal. It is speculated that the phenomenon of enhancement appears stronger than sometimes.

That is, according to the study by the present inventors, the relationship between the heart rate and the energy consumption can be expressed by a predetermined regression equation within a certain range, but the above-mentioned regression is achieved within a range where the heart rate enhancement phenomenon appears. It turns out that it can no longer be expressed by a formula. In other words, the above study revealed that the relationship between heart rate and energy consumption fluctuated. Further, it has been found that the fluctuation is caused by the influence of the user's activity content according to the expression pattern of the user's specific heart rate enhancement phenomenon, that is, the user's physical characteristics. Therefore, in the methods that the present inventors have studied so far, although the exercise intensity at a certain time point is taken into consideration, the influence of the user's activity content before that time according to the user's physical characteristics is considered. As a result, the estimation accuracy could not be improved.

Therefore, the present inventors have created an embodiment of the present disclosure that can estimate the energy consumption with high accuracy even from the heart rate by focusing on the above knowledge. . That is, according to the embodiment of the present disclosure described below, it is possible to estimate the energy consumption with high accuracy by considering the expression pattern of the heart rate enhancement phenomenon that the inventors have independently known. . For example, in the present embodiment, when a heart rate higher than the resting heart rate is detected after exercise of high exercise intensity, in this embodiment, the influence of the enhancement phenomenon on the heart rate is affected. Accurately grasp the contribution and estimate the energy consumption after excluding the contribution. Hereinafter, the information processing apparatus and the information processing method according to the embodiment of the present disclosure will be sequentially described in detail.

<< 2. Embodiment according to the present disclosure >>
<2.1. Overview of Information Processing System 1 According to the Present Embodiment>
Next, a configuration according to an embodiment of the present disclosure will be described. First, a configuration according to an embodiment of the present disclosure will be described with reference to FIG. FIG. 1 is an explanatory diagram illustrating a configuration example of an information processing system 1 according to the present embodiment.

As shown in FIG. 1, the information processing system 1 according to the present embodiment includes a wearable device 10, a server 30, and a user terminal 50, which are connected to each other via a network 70 so as to communicate with each other. Specifically, the wearable device 10, the server 30, and the user terminal 50 are connected to the network 70 via a base station (not shown) or the like (for example, a mobile phone base station, a wireless LAN access point, or the like). Note that any method can be applied to the network 70 regardless of whether it is wired or wireless, but it is desirable to use a communication method that can maintain stable operation.

Wearable device 10 can be a device that can be worn on a part of the user's body, or an implant device (implant terminal) inserted into the user's body. More specifically, the wearable device 10 has various methods such as HMD (Head Mounted Display) type, ear device type, anklet type, bracelet type, collar type, eyewear type, pad type, batch type, and clothing type. Wearable devices can be employed. Furthermore, the wearable device 10 incorporates sensors such as a heart rate sensor that detects a user's heart rate (or a pulse sensor that detects the user's pulse rate) and an acceleration sensor that detects exercise intensity due to the user's exercise. Details of the wearable device 10 will be described later.

The server 30 is configured by, for example, a computer. For example, the server 30 stores information used in the present embodiment, and distributes information provided by the present embodiment. Details of the server 30 will be described later.

The user terminal 50 is a terminal for outputting information provided by the present embodiment to a user or the like. For example, the user terminal 50 can be a device such as a tablet PC (Personal Computer), a smartphone, a mobile phone, a laptop PC, a notebook PC, or an HMD.

In FIG. 1, the information processing system 1 according to the present embodiment is illustrated as including one wearable device 10 and a user terminal 50, but is not limited to this in the present embodiment. . For example, the information processing system 1 according to the present embodiment may include a plurality of wearable devices 10 and user terminals 50. Furthermore, the information processing system 1 according to the present embodiment may include other communication devices such as a relay device for transmitting information from the wearable device 10 to the server 30. In the present embodiment, the wearable device 10 may be used as a stand-alone device. In this case, at least some of the functions of the server 30 and the user terminal 50 are performed in the wearable device 10.

<2.2. Configuration of Wearable Device 10 According to this Embodiment>
Next, the configuration of the wearable device 10 according to the embodiment of the present disclosure will be described with reference to FIGS. FIG. 2 is a block diagram illustrating a configuration of the wearable device 10 according to the present embodiment. 3 and 4 are explanatory diagrams illustrating an example of the appearance of the wearable device 10 according to the present embodiment. FIG. 5 is an explanatory diagram illustrating an example of a wearing state of the wearable device 10 according to the present embodiment.

As shown in FIG. 2, the wearable device 10 includes an input unit (acquisition unit) 100, an output unit 110, a sensor unit (acquisition unit) 120, a control unit 130, a communication unit 140, and a storage unit 150. Has mainly. Below, the detail of each function part of the wearable device 10 is demonstrated.

(Input unit 100)
The input unit 100 receives input of data and commands to the wearable device 10. More specifically, the input unit 100 is realized by a touch panel, a button, a microphone, a drive, or the like. For example, the input unit 100 includes information (cluster information, heart rate fluctuation pattern data, consumption energy fluctuation pattern data, etc.) used for learning by a learning unit 132 described later, a classification unit 134 and an estimation unit 136 described later. Information (cluster information, heart rate fluctuation pattern data, energy consumption fluctuation pattern data, etc.) to be used for classification and estimation is input.

(Output unit 110)
The output unit 110 is a device for presenting information to the user. For example, the output unit 110 outputs various types of information to the user by image, sound, light, vibration, or the like. Specifically, in order to acquire a fluctuation pattern of the heart rate at a change in a predetermined exercise intensity, the output unit 110 serves as an instruction unit such as a screen or sound that prompts the user to perform a predetermined exercise Is output. Further, the output unit 110 outputs, as a notification unit, information related to energy consumption estimated by the control unit 130 described later, or outputs information for recommending a predetermined exercise based on the estimated energy consumption. . The output unit 110 is realized by a display, a speaker, an earphone, a light emitting element, a vibration module, or the like. Note that the function of the output unit 110 may be provided by the output unit 510 of the user terminal 50 described later.

(Sensor unit 120)
The sensor unit 120 is provided in the wearable device 10 worn on the user's body, and includes a heart rate sensor (heart rate monitor) that detects the user's heart rate. The heart rate sensor measures the heart rate of the user and outputs the measurement result to the control unit 130 described later. The heart rate sensor may be a pulse sensor (pulse meter) that measures the user's pulse rate. The sensor unit 120 may include a motion sensor for detecting the exercise intensity of the user. The motion sensor includes at least an acceleration sensor (accelerometer), detects a change in acceleration caused by a user's operation, and outputs a detection result to the control unit 130 described later. In the embodiment described below, an acceleration change generated in accordance with a user's action is used as an index indicating exercise intensity. Since the acceleration can be measured by an acceleration sensor, and even an ordinary person can easily use the acceleration sensor, the acceleration change is used as an index indicating the exercise intensity here. That is, the sensor unit 120 includes information (heart rate variation pattern data and the like) used for learning by a learning unit 132 described later, and information (heart rate) used for classification and estimation by a classification unit 134 and an estimation unit 136 described later. Number variation pattern data, exercise intensity, etc.).

Note that the motion sensor may include a gyro sensor, a geomagnetic sensor, and the like. Furthermore, the sensor unit 120 may include various other sensors such as a GPS (Global Positioning System) receiver, an atmospheric pressure sensor, a temperature sensor, and a humidity sensor. Further, the sensor unit 120 may include a clock mechanism (not shown) that grasps an accurate time, and may associate the acquired time of the heart rate and the like with the acquired heart rate and acceleration change.

(Control unit 130)
The control unit 130 is provided in the wearable device 10, and can control each block of the wearable device 10, or can perform calculation using the heart rate and acceleration change output from the sensor unit 120 described above. . The control unit 130 is realized by hardware such as a CPU (Central Processing Unit), a ROM (Read Only Memory), and a RAM (Random Access Memory). Note that the function of the control unit 130 may be provided by the control unit 330 of the server 30 or the control unit 530 of the user terminal 50 described later.

Furthermore, the control unit 130 can also function as a learning unit (learning device) 132, a classification unit 134, and an estimation unit 136. That is, the control unit 130 estimates energy consumption based on the relationship between the heart rate and energy consumption. Classification can be performed to perform estimation or learning can be performed. Details of these functional units of the control unit 130 will be described later.

(Communication unit 140)
The communication unit 140 is provided in the wearable device 10 and can transmit and receive information to and from external devices such as the server 30 and the user terminal 50. In other words, it can be said that the communication unit 140 is a communication interface having a function of transmitting and receiving data. The communication unit 140 is realized by a communication device such as a communication antenna, a transmission / reception circuit, or a port.

(Storage unit 150)
The storage unit 150 is provided in the wearable device 10 and stores a program, information, and the like for the above-described control unit 130 to execute various processes and information obtained by the processes. The storage unit 150 is realized by, for example, a non-volatile memory such as a flash memory.

In the present embodiment, the two sensors of the sensor unit 120, the heart rate sensor and the motion sensor, may be provided in separate wearable devices 10. By doing in this way, since the structure of each wearable device 10 can be made compact, it becomes possible to mount | wear the said wearable device 10 to various site | parts of a user's body.

As described above, the wearable device 10 can employ various types of wearable devices such as an eyewear type, an ear device type, a bracelet type, and an HMD type. In FIG. 3, an example of the external appearance of the wearable device 10 is shown. The wearable device 10a shown in FIG. 3 is an ear device type wearable device worn on both ears of a user. The wearable device 10a mainly includes left and right

main body portions

12L and 12R, and a neckband 14 that connects the

main body portions

12L and 12R. The

main body units

12L and 12R include, for example, at least a part of the input unit 100, the output unit 110, the sensor unit 120, the control unit 130, the communication unit 140, and the storage unit 150 illustrated in FIG. In addition, the

main body portions

12L and 12R incorporate an earphone (not shown) that functions as the output portion 110, and the user can listen to audio information and the like by wearing the earphone in both ears.

Further, FIG. 4 shows another example of the appearance of the wearable device 10. A wearable device 10b shown in FIG. 4 is a bracelet-type wearable device. The wearable device 10b is a wearable terminal worn on a user's arm or wrist, and is also referred to as a wristwatch type wearable device. The wearable device 10b is provided with a touch panel display 16 having functions as the input unit 100 and the output unit 110 in FIG. Furthermore, the outer peripheral surface is provided with a speaker 18 having a sound output function as the output unit 110 and a microphone 20 having a sound collection function as the input unit 100.

Further, as shown in FIG. 5, one or a plurality of wearable devices 10 can be attached to various parts such as a user's head and wrist.

<2.3. Configuration of Server 30 According to this Embodiment>
Next, the configuration of the server 30 according to the embodiment of the present disclosure will be described with reference to FIG. FIG. 6 is a block diagram illustrating a configuration of the server 30 according to the present embodiment.

As described above, the server 30 is configured by a computer, for example. As illustrated in FIG. 6, the server 30 mainly includes an input unit 300, an output unit 310, a control unit 330, a communication unit 340, and a storage unit 350. Below, the detail of each function part of the server 30 is demonstrated.

(Input unit 300)
The input unit 300 receives input of data and commands to the server 30. More specifically, the input unit 300 is realized by a touch panel, a keyboard, or the like.

(Output unit 310)
The output unit 310 includes, for example, a display, a speaker, a video output terminal, an audio output terminal, and the like, and outputs various types of information using an image or audio.

(Control unit 330)
The control unit 330 is provided in the server 30 and can control each block of the server 30. The control unit 330 is realized by hardware such as a CPU, a ROM, and a RAM, for example. Note that the control unit 330 may execute a part of the functions of the control unit 130 of the wearable device 10.

(Communication unit 340)
The communication unit 340 is provided in the server 30 and can transmit and receive information to and from external devices such as the wearable device 10 and the user terminal 50. Note that the communication unit 340 is realized by a communication device such as a communication antenna, a transmission / reception circuit, or a port.

(Storage unit 350)
The storage unit 350 is provided in the server 30 and stores a program for the control unit 320 described above to execute various processes and information obtained by the processes. More specifically, the storage unit 350 includes data such as heart rate and energy consumption acquired from the wearable device 10 worn by a plurality of users, map data provided to each user, and data used for estimating energy consumption. Etc. can be stored. The storage unit 350 is realized by a magnetic recording medium such as a hard disk (HD), a nonvolatile memory, or the like, for example.

<2.4. Configuration of User Terminal 50 According to the Present Embodiment>
Next, the configuration of the user terminal 50 according to the embodiment of the present disclosure will be described with reference to FIGS. 7 and 8. FIG. 7 is a block diagram illustrating a configuration of the user terminal 50 according to the present embodiment. Moreover, FIG. 8 is explanatory drawing which shows an example of the external appearance and usage type of the user terminal 50 which concerns on this embodiment.

As described above, the user terminal 50 can be a device such as a tablet PC or a smartphone. As illustrated in FIG. 7, the user terminal 50 mainly includes an input unit 500, an output unit 510, a control unit 530, and a communication unit 540. Below, the detail of each function part of the user terminal 50 is demonstrated.

(Input unit 500)
The input unit 500 receives input of data and commands to the user terminal 50. More specifically, the input unit 500 is realized by a touch panel, a keyboard, or the like.

(Output unit 510)
The output unit 510 includes, for example, a display, a speaker, a video output terminal, an audio output terminal, and the like, and outputs various types of information using an image or audio. Note that the output unit 510 can also function as the output unit 110 of the wearable device 10 as described above.

(Control unit 530)
The control unit 530 is provided in the user terminal 50 and can control each block of the user terminal 50. The control unit 530 is realized by hardware such as a CPU, a ROM, and a RAM, for example.

(Communication unit 540)
The communication unit 540 can exchange information with an external device such as the server 30. The communication unit 540 is realized by a communication device such as a communication antenna, a transmission / reception circuit, or a port.

As described above, as the user terminal 50, a device such as a tablet PC or a smartphone can be employed. In FIG. 8, an example of the external appearance of the user terminal 50a of a tablet-type PC is shown. For example, as shown on the left side of FIG. 8, the user terminal 50a is mounted on the treadmill 52 using a mounting gear 54 for mounting the user terminal 50a. As shown in FIG. 8, when the user terminal 50 a is mounted, a display as the output unit 510 of the user terminal 50 a can be visually recognized by a user who trains using the treadmill 52.

<2.5 Configuration of Control Unit 130 According to the Present Embodiment>
Below, the structure of the control part 130 which concerns on this embodiment is demonstrated with reference to FIGS. 9-14. 9 and 10 are explanatory diagrams for explaining the operation of the learning unit 132 according to the present embodiment. 11 to 13 are explanatory diagrams for explaining the operation of the likelihood estimator 236 according to the present embodiment. Further, FIG. 14 is an explanatory diagram for explaining the operation of the estimation unit 136 according to the present embodiment. As described above, the control unit 130 mainly includes three functional units, that is, a learning unit 132, a classification unit 134, and an estimation unit 136. Below, each function part which control part 130 has is explained.

(Learning unit 132)
For each cluster, the learning unit 132 performs machine learning using a heart rate fluctuation pattern due to a change in exercise intensity belonging to the cluster and a consumption energy fluctuation pattern measured simultaneously with the heart rate fluctuation pattern. And the learning part 132 acquires the relationship information which shows the relationship between the fluctuation pattern of the heart rate by the change of exercise intensity, and the fluctuation pattern of consumption energy by the said machine learning for every cluster.

Here, a cluster refers to a group of data with a similar tendency that can be estimated using the same model. Specifically, in this embodiment, the tendency of the fluctuation pattern of the heart rate due to the change of exercise intensity is similar, in other words, the tendency of the pattern in which the heart rate enhancement phenomenon appears is similar. Time series data is handled as belonging to the same cluster. Since time series data of multiple heart rates belonging to the same cluster tend to be similar to each other, it is possible to estimate time series data of energy consumption from time series data of heart rates using a common model. It is considered possible. Therefore, the learning unit 132 is a model that takes into account the expression pattern of the heart rate enhancement phenomenon related to the corresponding cluster in each cluster, and the relationship between the fluctuation pattern of the heart rate due to the change in exercise intensity and the fluctuation pattern of the consumed energy. The relationship information indicating is acquired. Each acquired relationship information is used when estimation is performed in an estimator for each cluster included in the estimation unit 136 described later. In other words, in this embodiment, there is an estimator for each cluster, and the learning unit 132 prepares the relationship information for each cluster for use in estimation of the estimator linked to the cluster.

More specifically, the learning unit 132 can perform learning as follows. As shown in FIG. 9, the learning unit 132 receives a plurality of fluctuation patterns of heart rate due to a change in exercise intensity acquired by wearing the above-described wearable device 10 with respect to a plurality of users. Here, acceleration time-series data 400 indicating a change in exercise intensity and heart-rate time-series data 402 corresponding to the acceleration time-series data 400 are used as a heart rate fluctuation pattern due to a change in exercise intensity. Yes. The input acceleration and heart rate time-series data 400 and 402 have clusters as labels 420. Note that the data input to the learning unit 132 is not limited to such acceleration and heart rate time-series data 400 and 402, and is, for example, a heart rate fluctuation pattern in a known exercise intensity change. May be. Furthermore, the input heart rate time-series data 402 includes an expression pattern of an enhancement phenomenon. Then, the learning unit 132 extracts feature points and feature amounts of the time series data 400 and 402 in each cluster by using machine learning using a recurrent neural network or the like, and generates a classification database 234. The classification database generated here can be used to search for clusters when estimating energy consumption. Furthermore, as shown in FIG. 10, the learning unit 132 includes time series data 400 and 402 of acceleration and heart rate belonging to the same cluster, and time series data 404 (energy consumption) of energy consumption acquired by breath measurement at the same time. Measured value). The learning unit 132 performs supervised machine learning using a recurrent neural network or the like using the time series data 400, 402, and 404 as an input signal and a teacher signal, respectively. The learning unit 132 acquires relation information indicating the relationship between the time series data 400 and 402 of acceleration and heart rate and the time series data 404 of energy consumption by the machine learning described above. The learning unit 132 constructs an estimation database 240 that stores the acquired relation information for each cluster. The estimation database 240 constructed for each cluster is used for estimation of energy consumption.

Note that the learning unit 132 may perform machine learning using a semi-supervised learning device in order to omit labeling of some time series data 400 and 402 of acceleration and heart rate. In this case, the learning unit 132 compares the unlabeled acceleration and heart rate time series data 400 and 402 determined to be similar to the labeled acceleration and heart rate time series data 400 and 402. By learning to belong to the cluster, it is possible to improve the classification ability. The learning unit 132 may perform weak teacher learning using, for example, a question relating to body characteristics to the user and using cluster information determined based on an answer to the question as a rough teacher signal. Alternatively, the learning unit 132 may perform unsupervised learning that automatically performs cluster extraction using a large amount of data. In this case, the learning unit 132 automatically generates a cluster.

In the present embodiment, the learning unit 132 uses the time series data 400, 402, and 404 of acceleration, heart rate, and consumed energy belonging to the same cluster, and relationship information that indicates the relationship between the heart rate and consumed energy. Is getting. Since these time-series data 400, 402, and 404 belonging to the same cluster have similar tendencies, that is, similar expression patterns of heart rate enhancement phenomenon, specific relationship information is obtained from machine learning as described above. It is easy to find out. In order to construct the estimation database 240 related to one cluster, it is preferable to use time series data 400, 402, 404 obtained from at least several subjects. However, the construction of the estimation database 240 in the present embodiment is not limited to using the time series data 400, 402, and 404 obtained by performing measurement on the subject. For example, a part of the time series data 400, 402, 404 used for constructing the database 240 may be dummy time series data that artificially reproduces the tendency in the corresponding cluster. In the present embodiment, the learning method in the learning unit 132 is not limited to the method using machine learning described above, and other learning methods may be used.

(Classification part 134)
The classification unit 134 classifies which of a plurality of clusters the input data belongs to before performing estimation by the estimation unit 136 described later. Further, the input data is input to an estimator related to the cluster to which the data belongs, and is used for estimation of energy consumption. Specifically, the classification unit 134 includes a heart rate fluctuation pattern (for example, heart rate time-series data) due to a change in input exercise intensity and a model (for example, a heart rate time series) associated with each cluster. Data) and a model having the smallest difference between the input fluctuation pattern and the model is searched based on the comparison result. Alternatively, the classification unit 134 searches for a model in which the variation pattern and the model are most similar. Then, the heart rate fluctuation pattern is classified as belonging to the cluster related to the searched model. In other words, the classification unit 134 searches for a cluster corresponding to the expression pattern of the enhancement phenomenon having the same tendency based on the expression pattern of the enhancement phenomenon of the heart rate of each user. The estimator associated with each cluster performs estimation taking into account the tendency of data belonging to each cluster, that is, the expression pattern of the heart rate enhancement phenomenon, so that the estimation accuracy is improved by using such an estimator. Can be made.

More specifically, the classification unit 134 may use the classification database 234 generated by the learning unit 132. In this way, the classification unit 134 can search for a cluster to which a plurality of fluctuation patterns of heart rate due to changes in exercise intensity newly acquired for estimation belong.

Further, the classification unit 134 may perform classification by estimating likelihood, for example. The classification using the likelihood will be described with reference to FIGS. Likelihood is an index that indicates the reliability or probability of estimation based on input data. In this case, an estimator for estimating energy consumption for each cluster is prepared in advance. First, in each estimator, acceleration time-series data 400 indicating a change in exercise intensity, and heart rate time-series data 402 corresponding to the acceleration time-series data 400, as a heart rate fluctuation pattern due to a change in exercise intensity, Is input, and time series data 406 of energy consumption is estimated. Here, in order to distinguish from the time series data 404 (consumed energy consumption value) of the consumed energy acquired by the exhalation measurement, the estimated time series data 406 of the estimated consumed energy is used as the time series data 406 of the estimated consumed energy. Call it.

Further, the classification unit 134 has a plurality of likelihood estimators 236 as shown in FIG. The likelihood estimator 236 is provided so as to correspond to the estimator prepared for each cluster, and calculates the estimation likelihood by the corresponding estimator. Specifically, the likelihood estimator 236 includes the above-described acceleration time-series data 400, heart rate time-series data 402, time-series data 406 of estimated consumption energy by the corresponding estimator, and simultaneously by expiration measurement. The acquired time series data 404 of consumed energy is input. Then, the likelihood estimator 236 calculates an estimated likelihood 408 using these input data. The likelihood estimator 236 generates a likelihood estimation database 238 including the estimated likelihood 408 obtained in this way. Each likelihood estimator 236 calculates the estimated likelihood 408 as described above.

Furthermore, as shown in FIG. 12, the classification unit 134 compares the estimated likelihoods 408 calculated by the respective likelihood estimators 236. High estimation likelihood 408 means that estimation is performed with high reliability using time series data 400 and 402 of acceleration and heart rate. Therefore, it can be said that the estimator and the cluster having the highest estimated likelihood 408 are the most suitable estimator and cluster for the time series data 400 and 402 of the acceleration and the heart rate. Therefore, the time series data 400 and 402 of acceleration and heart rate are classified as belonging to the cluster related to the estimator corresponding to the likelihood estimator 236 having the highest estimated likelihood 408. For example, in the example of FIG. 12, since the estimated likelihood 408b calculated by the likelihood estimator 236b of cluster 2 is the highest, the

time series data

400a and 402a of acceleration and heart rate are classified as belonging to cluster 2. Is done.

At this time, each likelihood estimator 236 may search for a numerical value of the parameter 410 such that the calculated estimated likelihood 408 becomes higher as shown in FIG. In this case, the classification unit 134 searches for a cluster to which the

time series data

400a and 402a of acceleration and heart rate belong, using the estimated likelihood 408 obtained after optimizing the numerical value of the parameter 410. Further, the optimized parameter 410 may be used in estimation by the estimation unit 136 described later. By using the parameter 410 optimized in this way in estimation, the estimation accuracy of energy consumption can be further improved.

Here, the parameter 410 can be, for example, a numerical value used for normalizing the time-series data 400 of the heart rate before being input to each estimator. In some cases, the energy consumption can be estimated with higher accuracy by normalizing the heart rate time-series data 400 with a predetermined value and inputting the normalized value into the estimator. More specifically, the parameter 410 can include a heart rate at a moderate exercise intensity (for example, a heart rate in running at about 9 km / h). It is known that when the heart rate time-series data 400 is normalized with such a heart rate and the consumed energy is estimated using the normalized heart rate time-series data 400, the estimation accuracy is improved. . Therefore, for example, the likelihood estimator 236 slightly shakes a value with a standard heart rate (for example, an average value of heart rates measured from a large number of subjects) at a moderate exercise intensity as a central value. The value of the parameter 410 that maximizes the estimated likelihood 408 can be searched (perturbation method). Instead of performing the search by the perturbation method, the normalization parameter may be acquired by causing the user to perform an exercise corresponding to a moderate exercise intensity and measuring the heart rate.

Examples of other parameters 410 include numerical values used when normalizing acceleration time-series data, numerical values for correcting acceleration time-series data in accordance with the behavior of each user, etc. Can be mentioned. Specifically, in the present embodiment, acceleration is used as an index indicating exercise intensity. However, the position of the portion where the acceleration sensor is attached and the user's movement habit (such as shaking a large arm portion even at low speeds) Etc., the relationship between exercise intensity and acceleration changes. Accordingly, the accuracy of estimation of energy consumption can be improved by correcting the time-series data of acceleration with an appropriate parameter 410 and inputting it to the estimator in accordance with the part where the acceleration sensor is mounted or the user's behavior. . In the present embodiment, the parameter 410 searched for in each likelihood estimator 236 is not limited to the above-described example, and any other parameter can be used as long as it can improve the estimation accuracy of energy consumption. It may be a parameter.

In the present embodiment, the classification method in the classification unit 134 is not limited to the method described above, and other methods may be used.

(Estimation unit 136)
As shown in FIG. 14, the estimation unit 136 is based on the relationship information stored in the estimation database 240 obtained by the learning unit 132 and newly acquired time series data 400 and 402 of the user's acceleration and heart rate. Thus, the time series data 406 of energy consumption is estimated. Since the estimation unit 136 performs estimation using the estimation database 240 prepared for each cluster, it can be said that the estimation unit 136 has a plurality of estimators prepared for each cluster. Specifically, the estimation unit 136 corresponds to the cluster to which the time series data 400 and 402 to which the time series data 400 and 402 searched by the above-described classifying unit 134 belongs is the newly acquired time series data 400 and 402 of the user's acceleration and heart rate. Input to the estimator (estimation database 240) to perform estimation. In this embodiment, the estimation unit 136 performs estimation based on relationship information prepared for each cluster having a similar heart rate fluctuation pattern, in other words, a similar heart rate enhancement phenomenon expression pattern. Do. Therefore, according to the present embodiment, since the estimation is performed in consideration of the enhancement phenomenon, the estimation accuracy of energy consumption can be improved. The energy consumption estimated by the estimation unit 136 is output to the user by the output unit 110, stored in the storage unit 150, or transmitted to the server 30 and the user terminal 50.

<2.6. Information Processing Method According to this Embodiment>
Heretofore, the configurations of the information processing system 1 according to the present embodiment and the wearable device 10, the server 30, and the user terminal 50 included in the information processing system 1 have been described in detail. Next, an information processing method according to the present embodiment will be described. The information processing method according to the present embodiment corresponds to a learning stage in which learning is performed to acquire relation information for estimating energy consumption, and a user's physical characteristics (such as an expression pattern of a user's heart rate enhancement phenomenon). Thus, it can be divided into two stages: an estimation stage for estimating energy consumption.

(Learning stage)
First, the learning stage will be described with reference to FIG. FIG. 15 is a flowchart for explaining an example of the learning stage of the information processing method according to the present embodiment. As shown in FIG. 15, the learning stage in the information processing method according to the present embodiment includes two steps, step S101 and step S103. Details of each step included in the learning stage of the information processing method according to the present embodiment will be described below.

(Step S101)
The instructor, the wearable device 10 or the user terminal 50 causes a plurality of users to repeatedly run, walk and rest on the treadmill every few minutes and repeatedly perform exercise with a predetermined exercise intensity. At this time, the user may be caused to perform a predetermined exercise by giving an instruction to the user by the instructor, the wearable device 10 or the user terminal 50. It is assumed that the predetermined exercise is an exercise that can grasp the expression pattern of the heart rate increase phenomenon of each user. During the exercise, the wearable device 10 worn on a part of each user's body measures each user's heart rate. Furthermore, the wearable device 10 measures the acceleration due to the user's movement using the built-in acceleration sensor. Moreover, the breath analysis apparatus worn on each user's face measures the oxygen concentration and the carbon dioxide concentration contained in each user's breath. By performing such measurement, it is possible to acquire time-series data including the expression pattern of the heart rate enhancement phenomenon that is used for learning by the learning unit 132.

(Step S103)
For each cluster, wearable device 10 performs machine learning using time series data 400 and 402 of acceleration and heart rate belonging to the cluster and time series data 404 of energy consumption measured simultaneously in step S101. The wearable device 10 acquires relationship information indicating the relationship between the time series data 400 and 402 of acceleration and heart rate and the time series data 404 of energy consumption by the machine learning. Furthermore, the wearable device 10 constructs an estimation database 240 storing the acquired relation information for each cluster. Since the details of the learning performed in step S103 have been described above, the description thereof is omitted here.

Note that the exercise in step S101 does not necessarily use a dedicated exercise device such as a treadmill, and may be, for example, jogging at a constant speed.

(Estimation stage)
Next, the estimation stage will be described with reference to FIG. FIG. 16 is a flowchart for explaining an example of the estimation stage of the information processing method according to the present embodiment. As shown in FIG. 16, the estimation stage in the information processing method according to the present embodiment mainly includes a plurality of steps from step S201 to step S205. Details of each step included in the estimation stage of the information processing method according to the present embodiment will be described below.

(Step S201)
The wearable device 10 attached to a part of the user's body measures acceleration and heart rate.

(Step S203)
The wearable device 10 searches for a cluster to which the time series data 400 of the user's acceleration and the time series data 402 of the heart rate obtained in step S201 belong. Since the search method has been described above, the description thereof is omitted here. Further, the wearable device 10 refers to the past history information about the user, and determines the cluster classified in the past as the time series data 400 of the user's acceleration and the time series data 402 of the heart rate obtained in step S201. It may be a cluster to which and belong. Further, a cluster input from the user by the input unit 100 may be a cluster to which the user belongs. In this way, the cluster search can be omitted. Furthermore, it is possible to present an estimated value of energy consumption to the user in a short time.

(Step S205)
Wearable device 10 estimates energy consumption using time series data 400 and 402 of acceleration and heart rate acquired in step S201 by the estimator related to the cluster selected in step S203.

In the example described above, the acceleration measured by the acceleration sensor is used as an index for the exercise intensity. However, the present embodiment is not limited to this. For example, exercise intensity is shown instead of acceleration. The index may be input by the user. In the above description, the learning stage and the estimation stage have been described separately. However, these stages may be performed continuously or alternately.

As described above, according to the present embodiment, energy consumption can be estimated with high accuracy. Specifically, in the present embodiment, the users are classified into clusters according to the tendency of fluctuation in the relationship between the energy consumption and the heart rate, that is, the expression pattern of the heart rate enhancement phenomenon. Since the trend of the relationship between the energy consumption and the heart rate of multiple users belonging to the same cluster is similar to each other, refer to the trend of the relationship change of a certain user in the cluster. It is also possible to grasp the tendency of other users to which the user belongs. Therefore, the energy consumption of other users in the same cluster can be estimated by using the tendency of change in the relationship of a certain user. Furthermore, the estimation takes into account the tendency of fluctuations in the relationship between energy consumption and heart rate according to the user, that is, the expression pattern of the heart rate enhancement phenomenon, thus improving the estimation accuracy of energy consumption. Can be made. Note that the tendency of the change in the relationship of a certain user to be referred to can be acquired in advance using breath measurement, so that the accuracy of estimation of energy consumption of other users in the same cluster can be improved. In other words, in this embodiment, energy consumption can be estimated for other users without performing exhalation measurement.

In particular, according to the present embodiment, energy consumption in exercise in a short time and exercise (motion) in daily life with low exercise intensity is also high according to this embodiment, which has been difficult with the devices that the inventors have studied so far. It is possible to estimate with accuracy.

Note that the construction of the estimation database 240 at the learning stage described above does not have to be performed in the wearable device 10, but is constructed in the server 30 or the like, and the database 240 is stored in the storage unit 150 when the wearable device 10 is manufactured or shipped. May be stored.

The measurement in step S101 or step S201 can be performed by instructing the user to perform a desired exercise by an instructor or the like, but is provided by the wearable device 10 or the like according to the present embodiment. An exercise application may be used. More specifically, the exercise application can be performed by explicitly instructing the user to perform an exercise with a predetermined exercise intensity. In this case, since the exercise intensity of the exercise performed by the user is known, it is possible to omit the acceleration measurement built in the wearable device 10 or using an acceleration sensor. Hereinafter, such an exercise application will be described with reference to FIGS. FIGS. 17 to 20 are explanatory diagrams for explaining examples of display screens 800 to 806 used when acquiring time-series data.

Specifically, the exercise application provided by the wearable device 10 or the user terminal 50 according to the present embodiment prompts the user to maintain a resting state in order to measure the heart rate of the user at rest. 800 is displayed. For example, as shown in FIG. 17, the screen 800 has a phrase such as “Measure heart rate at rest. Sit down for a while.” To prompt the user to maintain a resting state. including. In the upper part of the screen 800, a change over time of the measured heart rate is displayed.

Next, when the measurement of the heart rate of the user at rest is completed, the exercise application displays a screen 802 that prompts the user to perform exercise with a predetermined exercise intensity. For example, as shown in FIG. 18, in order to prompt the user to perform an exercise with a predetermined exercise intensity, a text such as “Measured heart rate at rest. Run at 9 km per hour.” including. Then, the user is prompted by such a screen 802 and performs a specified exercise using the treadmill 52 or the like.

Furthermore, the above exercise application maintains the end of exercise and the resting state for the user in order to obtain the expression pattern of the enhanced phenomenon in the heart rate after the end of the exercise after measuring the heart rate in the exercise of a predetermined exercise intensity. A screen 804 that prompts the user to perform is displayed. As shown in FIG. 19, the screen 804 is used to prompt the user to end the exercise and maintain a resting state, such as “Please stop the treadmill and keep it standing.” including.

Next, the exercise application displays a screen 806 for notifying the user of the end of the measurement after acquiring the expression pattern of the heart rate enhancement phenomenon. As illustrated in FIG. 20, the screen 806 includes a phrase such as “Exit exercise” in order to notify the user that the measurement is to be ended. Note that the screens 800 to 806 shown in FIGS. 17 to 20 described so far are merely examples, and the present embodiment is not limited to such screens.

In this way, the exercise application can cause the user to perform the exercise in step S201. In the above description, the description has been made on the assumption that the wearable device 10 has a display. However, even when there is no display, the user can be exercised in step S201. For example, as shown in FIG. 21, which is an explanatory diagram for explaining a method of inducing exercise for the user when acquiring time-series data, the wearable device 10 sends voice information to the user according to the exercise application. It may be output.

In addition, the implementation of the measurement in step S101 or step S201 is not limited to an explicit instruction from the exercise application as described above. For example, instead of an explicit instruction, an acceleration sensor of the wearable device 10 is used to detect a change point and a stable interval of exercise intensity due to a user's action, and a time series including an expression pattern of a heart rate enhancement phenomenon Data may be acquired. In this case, the acceleration sensor detects a stable section where the exercise intensity is constant, and acquires the heart rate measured at this time as the time-series data. Hereinafter, such a method will be described with reference to FIGS. FIGS. 22 to 25 are explanatory diagrams for explaining examples of display screens 808 to 814 used in other methods when acquiring time-series data.

Specifically, the wearable device 10 starts measuring the user's heart rate when detecting that the user is in a resting state for a predetermined time (for example, several minutes) or more. At that time, the wearable device 10 displays a screen 808 for notifying that the measurement is started, such as “Heart rate measurement has started” as shown in FIG.

Further, the wearable device 10 detects that “exercise has been detected” as shown in FIG. 23 in order to notify that the measurement is started when an exercise of a predetermined exercise intensity or more by the user is detected. A screen 810 including a phrase such as “” is displayed.

Next, when the wearable device 10 detects that the user has finished exercising and is in a resting state, as shown in FIG. 24, a screen 812 including words such as “the resting state has been detected”. And an increase phenomenon in the heart rate of the user after the exercise is measured.

Further, in the above-described series of measurements, when an expression pattern of an increase phenomenon in the user's heart rate is detected, the wearable device 10 “measures the change in the heart rate after exercise, as shown in FIG. 25. And the like "are displayed. Note that the screens 808 to 814 shown in FIGS. 22 to 25 described so far are merely examples, and the present embodiment is not limited to such screens.

In this way, by using the acceleration sensor, it includes the expression pattern of the heart rate enhancement phenomenon by the user's daily activities and daily exercises without instructing the user to perform exercise of a predetermined exercise intensity. Time series data can be acquired. In the above description, the wearable device 10 or the like has been described as having a display, but the wearable device 10 or the like is not limited to having a display. For example, as shown in FIG. 26, which is an explanatory diagram for explaining another method for inducing exercise to the user at the time of acquiring time series data, the wearable device 10 provides voice to the user in accordance with the exercise application. Information may be output.

Note that the exercise in step S201 is not necessarily performed using a dedicated exercise device such as a treadmill, and may be, for example, jogging at a constant speed.

<< 3. Example according to this embodiment >>
The details of the information processing method in the embodiment of the present disclosure have been described above. Furthermore, a specific example of an application that provides useful information to the user using the above-described embodiment will be described. In addition, the Example shown below is an example of the said application to the last, and the information processing which concerns on this embodiment is not limited to the following Example.

<3.1. Example 1>
The example described below relates to an application that provides useful information to the user because the above-described embodiment improves the estimation accuracy of energy consumption for each exercise. Such Example 1 is demonstrated with reference to FIG.27 and FIG.28. 27 and 28 are explanatory diagrams illustrating examples of the display screens 820 and 822 of Example 1 according to the present embodiment.

In this embodiment, as described above, since the estimation accuracy of the energy consumption of the exercise in each short time is improved, for example, the energy consumption of walking on a slope and walking on a flat road It is possible to grasp the difference. Therefore, using the estimation according to the present embodiment described above, the energy consumption in the daily activities of the user, which is a continuation of short-term exercise (micro exercise), is estimated with high accuracy, and it is beneficial based on the energy consumption estimated by the user Information can be provided. Such an embodiment will be described below.

Example 1A
In this embodiment, the estimated energy consumption for each micro exercise is notified to the user. For example, when a user's exercise (activity) over an integrated period (several minutes or more) in which energy consumption exceeding a predetermined threshold is estimated, the wearable device 10 uses the estimated energy consumption due to the exercise. Notify the user. At this time, the wearable device 10 can notify the user, for example, by displaying a screen 820 shown in FIG. Further, the wearable device 10 can acquire position information on which the user has performed the exercise by using a GPS receiver or the like built in the wearable device 10. Furthermore, since the wearable device 10 includes a gyro sensor, a geomagnetic sensor, and the like in addition to the acceleration sensor, it acquires detailed information on the content of exercise performed by the user by analyzing sensing information obtained from these sensors. can do. Therefore, the wearable device 10 can notify the user not only the estimated energy consumption but also the position information where the user performed the exercise and the detailed information of the exercise content.

More specifically, FIG. 27 shows a screen 820 that displays energy consumption when the user uses the stairs of the central ticket gate at AA station. Here, it is assumed that an escalator is attached to the stairs. Therefore, the wearable device 10 acquires the energy consumption estimated when the user uses the escalator on another day with reference to the past exercise history and the estimated energy consumption for the user. The wearable device 10 calculates a difference between the estimated energy consumption when the stairs are used and the estimated energy consumption when the escalator is used, and notifies the user of the calculated difference as a point. For example, the notified point is displayed at the bottom of the screen 820 in FIG. The point calculated as described above is that, when the user performs an exercise (activity) that places a greater load on the body, the amount of energy consumed is greater than when an exercise that does not put a load on the body is selected. It is shown in a format that can be easily understood by the user. Notifying the user of such points leads to the user feeling a little sense of accomplishment by performing an exercise that places a load on the body, and increases the motivation for the user to select an exercise that places a load on the body. be able to.

(Example 1B)
Next, an embodiment for notifying the user of the above points as an “exercise savings passbook” will be described with reference to FIG. FIG. 28 shows a screen 822 that displays a list of estimated energy consumption for each exercise performed by a user and the points corresponding to the estimated energy to the user as an “exercise savings passbook”. Specifically, in the upper part of the screen 822, as in FIG. 27, the energy consumption when the user uses the staircase of the AA station and the above points are shown. Further, in the middle of the screen 822, energy consumed by the user walking fast in BB town (more specifically, walking faster than the standard walking speed) and the above points are shown. The point in this case corresponds to, for example, a difference from the estimated consumption energy when the user walks at a standard walking speed at a distance equivalent to the fast walking. Furthermore, at the bottom of the screen 822, the sum of the points acquired by the user in a predetermined period (for example, one day, one week, etc.) is shown. That is, in the present embodiment, the estimated energy consumption by the micro-exercise detected individually and the points acquired by the micro-exercise are notified to the user like a savings passbook as shown in FIG. By notifying the points in this way, the user will think that he wants to acquire more points, so the user can be guided to naturally perform exercises (micro exercises) that put a load on the body. it can.

Furthermore, using the estimation of energy consumption according to the present embodiment, the user may be recommended for exercise (micro exercise) that places a load on the body. For example, in this embodiment, when it is detected that the user has reached a position where estimated energy consumption equal to or greater than a predetermined threshold is acquired by the user's past exercise, the wearable device 10 is equal to or greater than the predetermined threshold. Recommend exercise to the user for estimated energy consumption.

More specifically, the wearable device 10 detects that the user has arrived at a position (for example, a staircase) where estimated energy consumption equal to or greater than a predetermined threshold is acquired by the user's past motion by the built-in GPS receiver. If so, the total estimated energy consumption of the user on that day is referred to. As a result of the reference, when the sum of the estimated energy consumption of the user on the day is insufficient compared to the target value of the user's daily energy consumption, the wearable device 10 increases the estimated energy consumption to a predetermined threshold value or more. Such exercise (eg, “stair climbing”) is recommended to the user. More specifically, when the wearable device 10 is a bracelet type device, the vibration device provided as the output unit 310 of the wearable device 10 vibrates, and the above-described motion, that is, “step climb” is given to the user. May be recommended. In addition, when the wearable device 10 has a display as the output unit 310, by displaying “This is recommended” or the like at the position of the staircase on the map displayed on the display, May be recommended to the user.

In addition, the recommendation of the micro exercise which the wearable device 10 performs may be performed based on the target value of the user's daily energy consumption, or may be performed based on the number of points acquired as described above. Further, the wearable device 10 may determine whether or not to make a recommendation based on the past microexercise performance of the user. For example, the wearable device 10 refers to the past history, and when a specific tendency is observed with respect to the content of the micro exercise actually performed by the user due to the recommendation, the wearable device 10 adjusts the micro exercise according to the tendency. Make recommendations. Wearable device 10 may refer to other user's information accumulated in server 30, and may detect the position where the estimated consumption energy more than a predetermined threshold was acquired by the exercise of other users.

As described above, according to the estimation according to the present embodiment, it is possible to estimate with high accuracy the energy consumed in exercise (motion) in daily life with low exercise intensity. Therefore, by using the estimation, in this embodiment, not a special exercise with high exercise intensity (for example, running) but an operation normally performed in daily life (for example, "step climbing"). Can also be recommended as a micro-exercise.

<3.2. Example 2>
According to the estimation of the present embodiment described above, it is also possible to determine whether or not an increase phenomenon has occurred in the heart rate. In addition, by using the estimation according to the above-described embodiment, it is possible to estimate a condition (exercise intensity, etc.) or the like that causes a heart rate enhancement phenomenon in the user. Therefore, by using the above-described determination and estimation, it is possible to create an application that notifies the user that the enhancement phenomenon has occurred or recommends an exercise that causes the enhancement phenomenon. The embodiments described below relate to such applications. Such Example 2 will be described with reference to FIGS. 29 to 32. FIGS. 29 to 32 are explanatory diagrams illustrating examples of display screens 824 to 830 of Example 2 according to the present embodiment.

(Example 2A)
For example, the wearable device 10 can estimate the energy consumption taking into account the enhanced state from the newly acquired time-series data 400 and 402 of the user's acceleration and heart rate by the estimation of the present embodiment. On the other hand, by applying the energy consumption estimation according to the prior art, which has been studied by the present inventors, to the time series data 400 and 402 of the newly acquired acceleration and heart rate of the user, the enhancement phenomenon is taken into consideration. Energy consumption can be estimated without doing so. Thus, for example, by detecting that the difference between the estimated value that takes into account the enhanced state and the estimated value that does not take into account the enhanced state exceeds a certain threshold, the wearable device 10 exhibits an enhanced phenomenon for the user. Can be notified.

Therefore, in the present embodiment, the wearable device 10 detects the end of the user's exercise and determines whether or not a heart rate increase phenomenon has occurred when a decrease in the heart rate is observed thereafter. The determination result is notified to the user. Since the heart rate enhancement phenomenon occurs when a high load is applied to the user's body, by notifying that the heart rate enhancement phenomenon has occurred, the user can perform exercise that causes the enhancement phenomenon to occur. You can feel a sense of accomplishment. Furthermore, by performing such notification, it is possible to increase motivation for the user to perform an exercise that places a heavy load on the body.

(Example 2B)
In addition, as described above, the wearable device 10 uses the estimation according to the present embodiment described above to estimate the conditions (exercise intensity, etc.) that cause the heart rate increase phenomenon in the user. Can do. More specifically, the wearable device 10 refers to the user's past exercise intensity fluctuation pattern recording and the heart rate fluctuation pattern at that time, so that the exercise rate of the exercise intensity can be increased. Whether it is expressed (conditions) can be estimated. Therefore, the wearable device 10 can recommend an exercise in which the heart rate enhancement phenomenon appears to the user based on the exercise intensity in which the estimated heart rate enhancement phenomenon appears.

In the present embodiment, the wearable device 10 detects that the user is walking, and is compared with the estimated condition described above, and it is estimated that the heart rate enhancement phenomenon does not occur due to the detected walking. In some cases, it is recommended to the user that the heart rate increase phenomenon occurs. For example, as shown in FIG. 29, the wearable device 10 displays a screen 824 including words such as “Please increase the walking speed” and “Please maintain the current speed for 2 minutes”, so that the user can Induces the exercise of heart rate enhancement. In the present embodiment, the recommendation of exercise is not limited to the screen display as described above, and the exercise may be recommended to the user by voice information, vibration, or the like. Such a recommendation can increase the opportunity for the user to perform exercise with exercise intensity that causes an increase in heart rate.

(Example 2C)
In the following embodiment, the wearable device 10 detects that the user is exercising, and is detected by comparison with the above-described estimated condition (exercise intensity in which an increase in heart rate occurs). If it is estimated that the increased heart rate phenomenon is caused by the exercise, it is determined whether the increased heart rate phenomenon is generated. The wearable device 10 notifies the user when it is determined that the heart rate enhancement phenomenon has not occurred. More specifically, as shown in FIG. 30, the wearable device 10 has words such as “the training result has been achieved” and “the heart rate has returned more smoothly than before”. The user is notified by displaying a screen 826 including.

When the user newly exercises with an exercise intensity that causes an increase in heart rate in the past, if the increase in heart rate does not occur, the user's physical ability (respiratory function, etc.) ) Is estimated to have improved. Based on such inference, in the present embodiment, the user can feel an improvement in his / her physical ability by the notification as described above.

(Example 2D)
As described above, when a user's physical ability is improved, clusters belonging to a fluctuation pattern of heart rate due to a change in exercise intensity obtained from the user change, and energy consumption is estimated based on the fluctuation pattern. The estimator used for the switching is switched accordingly. Thus, an embodiment will be described below in which the user can feel an improvement in his / her physical ability by notifying when the cluster changes in this way.

More specifically, the wearable device 10 extracts time series data 400 and 402 of a plurality of recent accelerations and heart rates related to the user. Furthermore, wearable device 10 performs estimation of cluster likelihood shown in FIG. 12 using extracted time-series data 400 and 402. The wearable device 10 notifies the user when the identified cluster having the highest likelihood can be considered as a cluster having higher physical ability than the past cluster. More specifically, as shown in FIG. 31, the wearable device 10 displays a screen 828 including a phrase such as “physical ability has improved and has been upgraded to class B1,” and the cluster is switched. Notify that the physical ability has been improved from the result. In the present embodiment, the notification as described above allows the user to feel an improvement in his / her physical ability.

In the above description, an example in which attention is paid to the cluster has been described. However, in the present embodiment, the present invention is not limited to this, and the parameter 410 optimized at the time of classification may be noted. In this case, when the numerical value of the newly optimized parameter 410 has changed from the numerical value of the parameter 410 used for estimation in the past, it can be inferred that the user's physical ability has changed.

(Example 2E)
In Example 2C described above, the presence or absence of the enhancement phenomenon changes in the exercise of the predetermined exercise intensity according to the physical ability of the user. However, the presence or absence of the enhancement phenomenon also depends on the physical condition of the user. change. Therefore, in this embodiment, based on such an idea, the user can be notified of information related to the user's physical condition.

More specifically, the wearable device 10 refers to the user's past exercise intensity fluctuation pattern recording and the heart rate fluctuation pattern at that time, so that the exercise rate of the exercise intensity can be increased. It can be estimated whether it does not develop (conditions). Therefore, the wearable device 10 detects that the user is exercising, and increases the heart rate by the detected exercise as compared with the above-described estimated condition (exercise intensity that does not cause an increase in the heart rate). When it is estimated that the phenomenon does not occur, it is determined whether or not a heart rate enhancement phenomenon is occurring. When it is determined that the wearable device 10 is experiencing an increase in heart rate, the wearable device 10 is normally in a condition where the increase in the heart rate does not occur. The user is notified that the enhancement phenomenon has occurred, and notifies the user. More specifically, as shown in FIG. 32, the wearable device 10 “has a possibility of poor physical condition. Let's stop training.” “Today, the recovery of the heart rate after exercise is not likely. The screen 830 including words such as “” is displayed. By performing such notification, the user can grasp a physical condition that is not recognized by himself / herself and can avoid unreasonable training.

<< 4. Summary >>
As described above, according to the present embodiment, energy consumption can be estimated with high accuracy. Specifically, in the present embodiment, since the estimation is performed in consideration of the tendency of fluctuation in the relationship between the energy consumption and the heart rate according to the user, that is, the expression pattern of the heart rate enhancement phenomenon, The energy estimation accuracy can be improved.

The estimation of energy consumption in the above-described embodiment may be performed by using learning by Deep Neural Network (DNN) using a large amount of data. Even in this case, since the estimation is performed in consideration of the expression pattern of the heart rate enhancement phenomenon according to the user, the estimation accuracy of energy consumption can be improved.

<< 5. Hardware configuration >>
FIG. 34 is an explanatory diagram illustrating an example of a hardware configuration of the information processing apparatus 900 according to the present embodiment. In FIG. 34, the information processing apparatus 900 shows an example of the hardware configuration of the wearable device 10 described above.

The information processing apparatus 900 includes, for example, a CPU 950, a ROM 952, a RAM 954, a recording medium 956, an input / output interface 958, and an operation input device 960. Further, the information processing apparatus 900 includes a display device 962, an audio output device 964, an audio input device 966, a communication interface 968, and a sensor 980. In addition, the information processing apparatus 900 connects each component with a bus 970 as a data transmission path, for example.

(CPU950)
The CPU 950 includes, for example, one or more processors configured by an arithmetic circuit such as a CPU, various processing circuits, and the like, and a control unit that controls the entire information processing apparatus 900 (for example, the control unit 130 described above). Function as. Specifically, the CPU 950 functions in the information processing apparatus 900 such as the learning unit 132, the classification unit 134, and the estimation unit 136 described above.

(ROM 952 and RAM 954)
The ROM 952 stores programs used by the CPU 950, control data such as calculation parameters, and the like. The RAM 954 temporarily stores a program executed by the CPU 950, for example.

(Recording medium 956)
The recording medium 956 functions as the storage unit 150 described above, and stores various data such as data related to the information processing method according to the present embodiment and various applications. Here, examples of the recording medium 956 include a magnetic recording medium such as a hard disk and a nonvolatile memory such as a flash memory. Further, the recording medium 956 may be detachable from the information processing apparatus 900.

(Input / output interface 958, operation input device 960, display device 962, audio output device 964, and audio input device 966)
The input / output interface 958 connects, for example, an operation input device 960, a display device 962, and the like. Examples of the input / output interface 958 include a USB (Universal Serial Bus) terminal, a DVI (Digital Visual Interface) terminal, an HDMI (High-Definition Multimedia Interface) (registered trademark) terminal, and various processing circuits.

The operation input device 960 functions as, for example, the input unit 100 described above, and is connected to the input / output interface 958 inside the information processing apparatus 900.

The display device 962 functions as, for example, the output unit 110 described above, is provided on the information processing apparatus 900, and is connected to the input / output interface 958 inside the information processing apparatus 900. Examples of the display device 962 include a liquid crystal display and an organic EL display (Organic Electro-Luminescence Display).

The audio output device 964 functions as, for example, the output unit 110 described above, and is provided on the information processing apparatus 900 and connected to the input / output interface 958 inside the information processing apparatus 900, for example. The voice input device 966 functions as, for example, the input unit 100 described above, and is provided on the information processing apparatus 900, for example, and is connected to the input / output interface 958 inside the information processing apparatus 900.

It goes without saying that the input / output interface 958 can be connected to an external device such as an operation input device (for example, a keyboard or a mouse) external to the information processing apparatus 900 or an external display device.

Further, the input / output interface 958 may be connected to a drive (not shown). The drive is a reader / writer for a removable recording medium such as a magnetic disk, an optical disk, or a semiconductor memory, and is built in or externally attached to the information processing apparatus 900. The drive reads information recorded on the attached removable recording medium and outputs the information to the RAM 954. The drive can also write a record to a removable recording medium that is installed.

(Communication interface 968)
The communication interface 968 functions as a communication unit 340 for performing wireless or wired communication with an external device such as the server 30 via, for example, the network 70 described above (or directly). Here, as the communication interface 968, for example, a communication antenna and an RF (RADIO frequency) circuit (wireless communication), an IEEE 802.15.1 port and a transmission / reception circuit (wireless communication), an IEEE 802.11 port and a transmission / reception circuit (wireless communication). ), Or a LAN (Local Area Network) terminal and a transmission / reception circuit (wired communication).

(Sensor 980)
The sensor 980 functions as the sensor unit 120 described above. Further, the sensor 980 may include various sensors such as a pressure sensor.

Heretofore, an example of the hardware configuration of the information processing apparatus 900 has been shown. Note that the hardware configuration of the information processing apparatus 900 is not limited to the configuration shown in FIG. Specifically, each component described above may be configured by using a general-purpose member, or may be configured by hardware specialized for the function of each component. Such a configuration can be appropriately changed according to the technical level at the time of implementation.

For example, the information processing apparatus 900 does not include the communication interface 968 when communicating with an external apparatus or the like via a connected external communication device, or when configured to perform stand-alone processing. Also good. Further, the communication interface 968 may have a configuration capable of communicating with one or more external devices by a plurality of communication methods. In addition, the information processing apparatus 900 may have a configuration that does not include, for example, the recording medium 956, the operation input device 960, the display device 962, and the like.

In addition, the information processing apparatus 900 according to the present embodiment may be applied to a system including a plurality of apparatuses based on a connection to a network (or communication between apparatuses) such as cloud computing. Good. In other words, the information processing apparatus 900 according to the present embodiment described above can be realized as the information processing system 1 that performs processing according to the information processing method according to the present embodiment using a plurality of apparatuses, for example.

<< 6. Supplement >>
The embodiment of the present disclosure described above may include, for example, a program for causing a computer to function as the information processing apparatus according to the present embodiment, and a non-temporary tangible medium in which the program is recorded. Further, the program may be distributed via a communication line (including wireless communication) such as the Internet.

In addition, each step in the processing of each embodiment described above does not necessarily have to be processed in the order described. For example, the steps may be processed by changing the order as appropriate. Each step may be processed in parallel or individually instead of being processed in time series. Furthermore, the processing method of each step does not necessarily have to be processed according to the described method. For example, it may be processed by another function unit by another method.

The preferred embodiments of the present disclosure have been described in detail above with reference to the accompanying drawings, but the technical scope of the present disclosure is not limited to such examples. It is obvious that a person having ordinary knowledge in the technical field of the present disclosure can come up with various changes or modifications within the scope of the technical idea described in the claims. Of course, it is understood that it belongs to the technical scope of the present disclosure.

In addition, the effects described in this specification are merely illustrative or illustrative, and are not limited. That is, the technology according to the present disclosure can exhibit other effects that are apparent to those skilled in the art from the description of the present specification in addition to or instead of the above effects.

The following configurations also belong to the technical scope of the present disclosure.
(1) An acquisition unit that acquires a user's physical characteristics, and an estimator based on the relationship between the number of beats and energy consumption, and according to the user's physical characteristics, the estimator An information processing apparatus that estimates energy consumption by activities performed by the user from the number of motions.
(2) The information processing apparatus according to (1), wherein the energy consumption is estimated by the estimator according to a fluctuation pattern of the number of beats of the user due to a change in exercise intensity of an activity performed by the user. .
(3) The information according to (2), wherein the energy consumption is estimated by the estimator according to a pattern of an increase in the number of beats of the user due to a change in exercise intensity of an activity performed by the user. Processing equipment.
(4) The information according to (1), including a plurality of the estimators, selecting one estimator according to the physical characteristics of the user, and estimating the energy consumption by the selected estimator. Processing equipment.
(5) A variation pattern of the number of beats of the user due to a change in exercise intensity of the activity performed by the user, and a variation pattern of the number of beats due to a change in predetermined exercise intensity linked to each estimator. The information processing apparatus according to (4), wherein the estimator is selected according to a comparison result.
(6) A cluster to which the fluctuation pattern of the user's pulsation belongs is searched based on a fluctuation pattern of the user's pulsation due to a change in exercise intensity of the activity performed by the user, The information processing apparatus according to (4), wherein the attached estimator is selected.
(7) The search for the cluster to which the fluctuation pattern of the user's pulsation belongs belongs to the fluctuation pattern of the user's pulsation due to a change in exercise intensity of the user's activity and the number of pulsations. Each estimated likelihood in each estimator using the variation pattern of the energy consumption corresponding to the variation pattern of the energy consumption and the variation pattern of the energy consumption estimated by inputting the variation pattern of the number of beats to each estimator. The information processing apparatus according to (6), which is performed by calculating a degree and comparing the calculated estimated likelihoods.
(8) The information processing apparatus according to (7), wherein a parameter for increasing the estimated likelihood is searched.
(9) For each of the clusters, using the fluctuation pattern of the number of beats due to a change in predetermined exercise intensity belonging to the cluster, and the fluctuation pattern of the energy consumption corresponding to the fluctuation pattern of the number of beats, The information processing apparatus according to any one of (6) to (8), further including a learning device that performs machine learning on a relationship between the number and energy consumption.
(10) The information processing apparatus according to (2) or (3), wherein the change in exercise intensity is acquired by an accelerometer attached to the user.
(11) The above (2) or (3) further includes an instruction unit that prompts the user to perform a predetermined exercise to acquire a fluctuation pattern of the user's pulsation rate due to a change in exercise intensity. The information processing apparatus described.
(12) The information processing apparatus according to any one of (1) to (11), further including a notification unit that notifies the user of the estimated energy consumption.
(13) The information processing apparatus according to (12), wherein the notification unit performs notification that recommends a predetermined exercise to the user based on the estimated energy consumption.
(14) The apparatus according to (4), further including a notification unit that notifies the user when the estimator other than the estimator selected in the past is selected according to the physical characteristics of the user. Information processing device.
(15) The information processing apparatus according to any one of (1) to (14), wherein the number of beats is acquired by a heart rate meter or a pulse meter attached to the user.
(16) The information processing apparatus is any one of the above (1) to (15), which is either a wearable terminal attached to the user's body or an implant terminal inserted into the user's body. Information processing apparatus described in one.
(17) Obtaining the user's physical characteristics, and based on the relationship between the number of beats corresponding to the user's physical characteristics and the consumed energy, the energy consumed by the user's activities from the number of beats of the user Estimating an information processing method.
(18) Based on the function of acquiring a user's physical characteristics and the relationship between the number of beats corresponding to the user's physical characteristics and the consumed energy, the energy consumed by the user's activities based on the number of beats of the user A program for causing a computer to realize a function for estimating

DESCRIPTION OF SYMBOLS 1

Information processing system

10, 10a, 10b

Wearable device

12L, 12R Main part 14 Neckband 16 Touch panel display 18 Speaker 20 Microphone 30

Server

50, 50a User terminal 52 Treadmill 54 Wearing gear 70

Network

90, 92 Change with

time

92a,

92b Section

100, 300, 500

Input unit

110, 310, 510 Output unit 120

Sensor unit

130, 330, 530 Control unit 132 Learning unit 134 Classification unit 136

Estimation unit

140, 340, 540

Communication unit

150, 350

Storage unit

234, 238, 240 DB
236 Likelihood estimator 400, 402, 404, 406 Time series data 408 Estimated likelihood 410 Parameter 420

Label

800, 802, 804, 806, 808, 810, 812, 814, 820, 822, 824, 826, 828, 830 Screen 900 Information processing device 950 CPU
952 ROM
954 RAM
956 Recording medium 958 Input / output interface 960 Operation input device 962 Display device 964 Audio output device 966 Audio input device 968 Communication interface 970 Bus 980 Sensor

Claims

An acquisition unit for acquiring the physical characteristics of the user;
An estimator based on the relationship between the number of beats and energy consumption;
With
According to the physical characteristics of the user, the estimator estimates energy consumption due to the activity performed by the user from the number of beats of the user.
Information processing device.
The information processing apparatus according to claim 1, wherein the energy consumption is estimated by the estimator according to a fluctuation pattern of the number of beats of the user due to a change in exercise intensity of an activity performed by the user.
3. The information processing apparatus according to claim 2, wherein the energy consumption is estimated by the estimator according to a pattern of an increase phenomenon of the number of pulsations of the user due to a change in exercise intensity of an activity performed by the user.
Comprising a plurality of the estimators;
Selecting one of the estimators according to the physical characteristics of the user, and estimating the energy consumption by the selected estimators;
The information processing apparatus according to claim 1.
The comparison result of the fluctuation pattern of the user's pulsation rate due to the change in the exercise intensity of the activity performed by the user and the fluctuation pattern of the pulsation rate due to the change of the predetermined exercise intensity associated with each estimator. The information processing apparatus according to claim 4, wherein the estimator is selected in response.
Based on the fluctuation pattern of the user's pulsation rate due to the change in exercise intensity of the activity performed by the user, a cluster to which the fluctuation pattern of the user's pulsation belongs belongs and is linked to the searched cluster. The information processing apparatus according to claim 4, wherein the estimator is selected.
The search for the cluster to which the fluctuation pattern of the user's pulsation belongs belongs to the fluctuation pattern of the pulsation of the user and the fluctuation pattern of the pulsation due to a change in exercise intensity of the activity of the user performed by the user. The estimated likelihood in each estimator is calculated using the variation pattern of the consumed energy corresponding to and the variation pattern of the consumed energy estimated by inputting the pulsation number variation pattern to each estimator. The information processing apparatus according to claim 6, wherein the information processing apparatus is performed by comparing the calculated estimated likelihoods.
The information processing apparatus according to claim 7, wherein a parameter that increases the estimated likelihood is searched.
For each cluster, using the fluctuation pattern of the number of beats due to a change in predetermined exercise intensity belonging to the cluster and the fluctuation pattern of the energy consumption corresponding to the fluctuation pattern of the number of beats, the number of beats and consumption The information processing apparatus according to claim 6, further comprising a learning device that performs machine learning on a relationship with energy.
The information processing apparatus according to claim 2, wherein the change in exercise intensity is acquired by an accelerometer attached to the user.
The information processing apparatus according to claim 2, further comprising: an instruction unit that prompts the user to perform a predetermined exercise in order to acquire a fluctuation pattern of the number of beats of the user due to a change in exercise intensity.
The information processing apparatus according to claim 1, further comprising a notification unit that notifies the user of the estimated energy consumption.
The information processing apparatus according to claim 12, wherein the notification unit notifies the user of a predetermined exercise based on the estimated energy consumption.
The information processing apparatus according to claim 4, further comprising: a notification unit configured to notify the user when the estimator other than the estimator selected in the past is selected according to the physical characteristics of the user. .
The information processing apparatus according to claim 1, wherein the number of beats is acquired by a heart rate meter or a pulse meter attached to the user.
The information processing apparatus according to claim 1, wherein the information processing apparatus is either a wearable terminal attached to the user's body or an implant terminal inserted into the user's body.
Obtaining the user's physical characteristics;
Based on the relationship between the number of pulsations according to the user's physical characteristics and the consumed energy, estimating the consumed energy due to the activity performed by the user from the number of pulsations of the user;
Including an information processing method.
The ability to acquire the user's physical characteristics;
Based on the relationship between the number of beats according to the user's physical characteristics and the consumed energy, the function of estimating the consumed energy due to the activity performed by the user from the number of beats of the user;
Is a program that makes a computer realize this.